AI-900 Question 17
Select 2A retail company wants to automate the process of counting the number of customers entering their store and analyze customer demographics such as age and gender. Which computer vision workloads would be most suitable for this scenario?
- A
Object detection
- B
Image classification
- C
Face analysis
- D
Optical character recognition (OCR)
- E
Semantic segmentation
Show answer and explanation
Correct answers: A, C
Explanation
To address the scenario, object detection is needed to count the number of customers by detecting people in images or video footage. Additionally, face analysis is required to extract demographic information like age and gender. These two workloads together meet the specified requirements effectively.
- A. Correct.
Object detection is the correct workload for identifying and counting customers entering the store, as it can detect and locate objects (people) in an image or video.
- B. Incorrect.
Image classification assigns a single label to an entire image, which is not sufficient for counting customers or analyzing demographics.
- C. Correct.
Face analysis is appropriate for extracting demographic information such as age and gender from detected faces, making it suitable for this use case.
- D. Incorrect.
Optical character recognition (OCR) is used for extracting text from images or documents, which is irrelevant to counting customers or analyzing demographics.
- E. Incorrect.
Semantic segmentation assigns a class to each pixel in an image, which is more suited for detailed scene understanding rather than counting people or analyzing demographics.